Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5040 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1364379 (Python Code)

Max Activating Token Index: 1

Text #1

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1371041 (Python Code)

Max Activating Token Index: 1

Text #2

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1366885 (Python Code)

Max Activating Token Index: 1

Text #3

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1366840 (Python Code)

Max Activating Token Index: 1

Text #4

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1364598 (Python Code)

Max Activating Token Index: 1

Text #5

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1368052 (Python Code)

Max Activating Token Index: 1

Text #6

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1373003 (Python Code)

Max Activating Token Index: 1

Text #7

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1374549 (Python Code)

Max Activating Token Index: 1

Text #8

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1370976 (Python Code)

Max Activating Token Index: 1

Text #9

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1360496 (Python Code)

Max Activating Token Index: 1

Text #10

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1364822 (Python Code)

Max Activating Token Index: 1

Text #11

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1368078 (Python Code)

Max Activating Token Index: 1

Text #12

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1369467 (Python Code)

Max Activating Token Index: 1

Text #13

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1365970 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1372262 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1373632 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1368516 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1367962 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1374739 (Python Code)

Max Activating Token Index: 1

Text #19

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1374249 (Python Code)

Max Activating Token Index: 1